Related Concept Videos
13:19Deep Neural Networks for Image-Based Dietary Assessment
03:31End-To-End Deep Neural Network for Salient Object Detection in Complex Environments
Reaction Mechanisms
For instance, the decomposition of ozone appears to follow a mechanism with two steps:
08:28Assessment of the Effects of Endocrine Disrupting Compounds on the Development of Vertebrate Neural Network Function Using Multi-electrode Arrays
09:48Neural Activity Propagation in an Unfolded Hippocampal Preparation with a Penetrating Micro-electrode Array
10:45Time-dependent Increase in the Network Response to the Stimulation of Neuronal Cell Cultures on Micro-electrode Arrays
You might also read
Related Articles
Articles linked to this work by shared authors, journal, and citation graph.
One-Pot Electrochemical Synthesis of (Hydroxyamino)methanesulfonate from CO<sub>2</sub>, Nitrate/Nitrite, and Sulfite.
Heterointerface‑Enabled Electrocatalysis for Efficient Energy Conversion.
Related Experiment Video
Updated: Jan 20, 2026

Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
Automatically Identifying Electrode Reaction Mechanisms Using Deep Neural Networks.
Gareth F Kennedy1, Jie Zhang1,2, Alan M Bond1,2
1School of Chemistry , Monash University , Clayton , Victoria 3800 , Australia.
This study introduces a deep neural network for objective electrochemical mechanism identification from cyclic voltammograms. The AI model achieves rapid and reliable classifications, overcoming human subjectivity in electrochemistry research.
More Related Videos
03:31Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
08:28Assessment of the Effects of Endocrine Disrupting Compounds on the Development of Vertebrate Neural Network Function Using Multi-electrode Arrays
Published on: April 26, 2018
Area of Science:
- Electrochemistry
- Machine Learning
- Computational Chemistry
Background:
- Electrochemical mechanism identification is currently subjective, relying on researcher experience.
- This subjectivity introduces bias and limits confidence in mechanism assignment.
- Objective and quantifiable methods are needed for accurate electrochemical analysis.
Purpose of the Study:
- To develop and validate a deep neural network (DNN) for objective identification of electrochemical mechanisms.
- To assess the DNN's performance in classifying cyclic voltammograms for common electrochemical reactions.
- To evaluate the impact of experimental factors on DNN classification accuracy.
Main Methods:
- Training a deep neural network on direct current (dc) cyclic voltammograms.
- Simulating experimental conditions including noise, uncompensated resistance, and scan rate variations.
- Testing the DNN with two distinct experimental datasets.
Main Results:
- The DNN achieved correct classification of electrochemical mechanisms within 5 milliseconds.
- The model demonstrated robustness against noise, uncompensated resistance, and scan rate variations.
- Accurate classifications were validated using real-world experimental data.
Conclusions:
- Deep neural networks offer a rapid, objective, and reliable alternative to subjective methods for electrochemical mechanism identification.
- The developed DNN provides a quantifiable measure of confidence in mechanism assignment.
- This approach has significant implications for advancing electrochemical research and diagnostics.